← Back to community benchmarks
Qwen3.6-27B-oQ6-fp16-mtp
Performance
16k
tokens
332.3
PP tok/s
15.5
TG tok/s
49310
TTFT (ms)
26.9
Peak mem (GB)
Hardware
Chip
M5 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 338.0 | 17.5 | 23.0 GB | view |
| 4k | 370.2 | 17.8 | 24.4 GB | view |
| 8k | 339.9 | 17.4 | 25.4 GB | view |
| 16k | 332.3 | 15.5 | 26.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 17.5 | 1.00× |
| 2× | 19.6 | 1.12× |
| 4× | 21.2 | 1.21× |